A Comparative Study of Azure Custom Vision Versus Google Vision API Integrated into AI Custom Models Using Object Classification for Residential Waste by Cosmina-Mihaela Rosca, Adrian Stancu, Marius Radu Tănase

“…The CWSM employs the LbfgsMaximumEntropyMulti algorithm and a dataset of 1000 records for training, divided equally across the categories. …”
Get full text

Ensemble modelling reveals spiny monkey orange (Strychnos spinosa Lam.) as a vulnerable wild edible fruit tree in West Africa by Hospice Gérard Gracias Avakoudjo, Mahunan Eric José Vodounnon, Rodrigue Idohou, Aly Coulibaly, Achille Ephrem Assogbadjo

“…Bioclimatic and soil variables were used at a resolution of 30 arcseconds with 588 occurrence records analysed using five algorithms (Random Forest (RF), Maximum Entropy (MaxEnt), Support Vector Machine (SVM), Boosted Regression Trees, and Generalized Linear Model (GLM)) and four global climate models (CanESM5, CNRM-CM6-1, HadGEM3-GC31-LL, and MIROC6). …”
Get full text

A study on improved random forest-based anomaly detection of regional tariff data under distributed photovoltaic access by Shujun Ji, Kai Liu, Bo Ling, Jiadong Li, Jinteng Wang, Xun Ma

“…With an oversampling factor of 0.6 and G-mean values consistently above 0.927, the method reliably completes anomaly detection for electricity price data across both low and high latitude regions.…”
Get full text

Classifying Power Quality Issues in Railway Electrification Systems Using a Nonsubsampled Contourlet Transform Approach by Pampa Sinha, Kaushik Paul, I. M. Elzein, Mohamed Metwally Mahmoud, Ali M. El‐Rifaie, Wulfran Fendzi Mbasso, Ahmed M. Ewais

“…NSCT's shift‐invariant, multiscale, and multidirectional capabilities allow for precise separation of oscillatory and transient components, while the split augmented Lagrangian shrinkage algorithm enhances decomposition efficiency. Features such as signal energy, entropy, and trend energy were extracted and visualized in a 3D feature space, demonstrating clear clustering for different PQ events. …”
Get full text

Advanced machine learning techniques reveal multidimensional EEG abnormalities in children with ADHD: a framework for automatic diagnosis by Ying Mao, Ying Mao, Xuchen Qi, Xuchen Qi, Xuchen Qi, Lingyan He, Shan Wang, Zhaowei Wang, Fang Wang, Fang Wang

“…., SHapley Additive exPlanations (SHAP) algorithm) to reveal brain function abnormalities between pediatric children with ADHD and healthy controls (HC) in a data-driven manner.MethodsMultidimensional EEG characteristics were extracted from multiple domain (including power spectral density (PSD), fuzzy entropy (FuzEn), and functional connectivity features of mutual information (MI)) using a publicly-available dataset. …”
Get full text

A Near-Infrared Imaging System for Robotic Venous Blood Collection by Zhikang Yang, Mao Shi, Yassine Gharbi, Qian Qi, Huan Shen, Gaojian Tao, Wu Xu, Wenqi Lyu, Aihong Ji

“…Furthermore, we optimize the AD-Census stereo matching algorithm by developing a variable-weight version, which improves its adaptability to image variations across different regions. …”
Get full text

A robust approach to satellite image encryption using chaotic map and circulant matrices by Shamsa Kanwal, Saba Inam, Asghar Ali Shah, Halima Iqbal, Anas Bilal, Muhammad Usman Hashmi, Raheem Sarwar

“…These findings verify the scheme's ability to come across the most stringent encryption and decryption standards, making it an effective solution for securing sensitive satellite image data.…”
Get full text

Climate Adaptation of Folk House Envelopes in Xinjiang Arid Region: Evaluation and Multi-Objective Optimization from Historical to Future Climates by Nurimaimaiti Tuluxun, Saierjiang Halike, Hao Liu, Buerlan Yelaixi, Kapulanbayi Ailaitijiang

“…This study develops a data-driven framework to assess and enhance building envelope performance across historical-to-future climate conditions (2007–2021 TMY data, 2024 observations, and 2050/2080 SSP3–7.0 projections) using the entropy-weighted TOPSIS method and NSGA-II algorithm. …”
Get full text

Integrated export instream coefficient model for accurate nonpoint source pollution estimation and management in the Yellow River Basin by Xueting Wang, Lei Wu, Yongkun Luo, Yimu Liu, Ruowen Wang

“…Empirical EC values were derived using genetic algorithm (GA) and Latin hypercube sampling, then improved EC and corrected EC were employed to estimate pollutant discharge and water inflow across land uses. …”
Get full text

Analysis of the Impact of Rain on Perception in Automated Vehicle Applications by Tim Brophy, Darragh Mullins, Ashkan Parsi, Jonathan Horgan, Enda Ward, Patrick Denny, Ciaran Eising, Brian Deegan, Martin Glavin, Edward Jones

“…The reliable performance of object detection perception algorithms in automated vehicles under adverse conditions such as rain is critical for maintaining vulnerable road user safety. …”
Get full text

Multidimensional Evaluation Framework and Classification Strategy for Low-Carbon Technologies in Office Buildings by Hongjiang Liu, Yuan Song, Yawei Du, Tao Feng, Zhihou Yang

“…The method includes four core components: (1) establishing three archetypal models—low-rise (H ≤ 24 m), mid-rise (24 m < H ≤ 50 m), and high-rise (50 m < H ≤ 100 m) office buildings—based on 99 office buildings in Beijing; (2) classifying 19 key technologies into three clusters—Envelope Structure Optimization, Equipment Efficiency Enhancement, and Renewable Energy Utilization—using bibliometric analysis and policy norm screening; (3) developing a four-dimensional evaluation framework encompassing Carbon Reduction Degree (CRD), Economic Viability Degree (EVD), Technical Applicability Degree (TAD), and Carbon Intensity Degree (CID); and (4) conducting a comprehensive quantitative evaluation using the AHP-entropy-TOPSIS algorithm. The results indicate distinct priority patterns across the building types: low-rise buildings prioritize roof-mounted photovoltaic (PV) systems, LED lighting, and thermal-break aluminum frames with low-E double-glazed laminated glass. …”
Get full text

Highly stable two-level current fluctuation in complex oxide heterostructures by Doyeop Kim, Jung-Woo Lee, Jihyun Lim, Sungjun Choi, Khimananda Acharya, Seobin Oh, Jaewhan Oh, Tula R. Paudel, Yongsoo Yang, Kitae Eom, Sunwoo Lee, Hyungwoo Lee

“…We utilize the stable two-level fluctuations to generate random bit-strings and confirm their applicability in practical stochastic machine learning algorithms for image super-resolution. This study provides a guideline for designing reliable entropy sources by exploiting the complementary interactions between cation and anion point defects in oxide-based electronic systems, essential for hardware-based random number generators.…”
Get full text

FLIP: A Novel Feedback Learning-Based Intelligent Plugin Towards Accuracy Enhancement of Chinese OCR by Xinyue Tao, Yueyue Han, Yakai Jin, Yunzhi Wu

“…This study develops FLIP (Feedback Learning-based Intelligent Plugin), a lightweight post-processing plugin designed to improve Chinese OCR accuracy across different systems without external dependencies. …”
Get full text

Exploring Brain Activity in Different Mental Cognitive Workloads by Sahar Oftadeh Balani, Ali Fawzi Al-Hussainy, Alhan Abd Al-Hassan Shalal, Mohammed Ubaid, Zinab Aluquaily, Jaafar Alamoori, Saeid Motevalli

“…After preprocessing to reduce noise and various artifacts and to obtain a clean signal for every subject, functional connectivity and complexity features were calculated from EEGs through the coherence and permutation entropy algorithms, respectively. Then, repeated measures analysis of variance (ANOVA) was conducted to assess the differences in complexity and connectivity measures across various brain regions between the rest and task states. …”
Get full text

The Optimization of Stand Structure Can Significantly Alleviate the Flammability of Forest Ecosystems by Yan Zhang, Xiangwen Deng, Xiaoyong He, Xiaolong Zhang, Zhihong Huang, Liang Chen, Shuai Ouyang, Wenhua Xiang

“…The principal component analysis (PCA), entropy weight method, k‐means clustering algorithm, and Pearson correlation coefficient method were employed for the classification of forest fuels and the evaluation of forest flammability. …”
Get full text

Synergizing neural networks with multi-objective thermal exchange optimization and PROMETHEE decision-making to improve PCM-based photovoltaic thermal systems by Yongxin Li, Ali Basem, As'ad Alizadeh, Pradeep Kumar Singh, Saurav Dixit, Hanaa Kadhim Abdulaali, Rifaqat Ali, Pancham Cajla, Husam Rajab, Kaouther Ghachem

“…Results demonstrated the model's high accuracy, with R2 values exceeding 0.998 across objectives. MOO based on GMDH-NN models using the novel multi-objective thermal exchange optimization (MOTEO) algorithm revealed trade-offs: maximizing EP and TP increased EG, highlighting inherent inefficiencies. …”
Get full text

REU-Net: A Remote Sensing Image Building Segmentation Network Based on Residual Structure and the Edge Enhancement Attention Module by Tianen Yuan, Bo Hu

“…This method provides a reliable foundation for the further optimization of building segmentation algorithms for remote sensing images.…”
Get full text

Prediction of Current and Future Distributions of Chalcophora detrita (Coleoptera: Buprestidae) Under Climate Change Scenarios by Arif Duyar, Muhammed Arif Demir, Mahmut Kabalak

“…An ensemble model was created by using 11 different algorithms (Artificial Neural Network, Classification Tree Analysis, eXtreme Gradient Boosting, Flexible Discriminant Analysis, Generalised Additive Model, Generalised Boosting Model, Generalised Linear Model, Multivariate Adaptive Regression Splines, Maximum Entropy, Random Forest, Surface Range Envelope) to predict the potential suitable habitats of C. detrita. …”
Get full text

Optimized Two-Stage Anomaly Detection and Recovery in Smart Grid Data Using Enhanced DeBERTa-v3 Verification System by Xiao Liao, Wei Cui, Min Zhang, Aiwu Zhang, Pan Hu

“…The first stage employs an optimized increment-based detection algorithm achieving 95.0% for recall and 54.8% for precision through multidimensional analysis. …”
Get full text

Forest classification and carbon stock estimation with integration of airborne LiDAR and satellite Gaofen-6 data in a subtropical region by Ruoqi Wang, Dengsheng Lu, Guiying Li, Yisa Li, Wenjing Liu

“…The inclusion of LCE variables consistently improved FCS estimation performance across all stratification schemes, while CHD-based stratification improved FSC estimation only when the LCE metrics were included. …”
Get full text